Cone beam computed tomography as a first line investigation in the pediatric dental patient

Prevalence and morphological features of molar-root incisor malformation in children attending a specialist paediatric dental unit

BACKGROUND

Molar-root incisor malformation (MRIM) is a rare dental anomaly featuring constricted cervical margins and tapered, narrow root and pulp morphology, often associated with severe toothache and infection.

AIM

The aim of this study was to determine the prevalence of MRIM in children seen in a specialist paediatric dental unit of a tertiary referral hospital and to describe the characteristics of affected individuals.

DESIGN

This study was an audit of children attending from November 2020 to November 2021. Radiographs were used to identify individuals with MRIM, and clinical data were collated. In addition, histology and microcomputed tomography (microCT) imaging were performed on teeth extracted from an affected individual.

RESULTS

The prevalence of MRIM was five cases of 1054 children examined (0.47% or 1:210). The permanent first molars were affected in all five children and the primary second molars in two children; all children had medical comorbidities and multiple exposures to general anesthesia before 4 years of age. In addition, histological and microCT analyses displayed numerous microchannels connecting the pulp chamber to the external surface of the tooth at the furcation.

CONCLUSIONS

Molar-root incisor malformation is an uncommon dental anomaly affecting paediatric patients with multiple comorbidities and is characterized by porosities extending from the pulp chamber to the external tooth surface, predisposing the risk of bacterial ingress from the oral cavity into the pulp chamber. Early detection may prevent atypical odontogenic facial pain and infection.

Analysis of the feasibility of using deep learning for multiclass classification of dental anomalies on panoramic radiographs

The aim of the feasibility study was to construct deep learning models for the classification of multiple dental anomalies in panoramic radiographs. Panoramic radiographs with single supernumerary teeth and/or odontomas were considered the "case" group; panoramic radiographs with no dental anomalies were considered the "control" group. The dataset comprised 150 panoramic radiographs: 50 each of no dental anomalies, single supernumerary teeth, and odontomas. To classify the panoramic radiographs into case and control categories, we employed AlexNet, which is a convolutional neural network model. AlexNet was able to classify whole panoramic radiographs into two or three classes, according to the presence or absence of supernumerary teeth or odontomas. The performance metrics of the three-class classification were 70%, 70.8%, 70%, and 69.7% for accuracy, precision, sensitivity, and F1 score, respectively, in the macro average. These results support the feasibility of using deep learning to detect multiple dental anomalies in panoramic radiographs.